logo

RAG Playground

RAG Playground

RAG Playground is an innovative platform that allows users to experiment with and compare different Retrieval-Augmented Generation (RAG) architectures. The platform supports uploading PDFs, querying across multiple RAG pipelines, and comparing outputs side-by-side. Features include PDF upload, multiple RAG architecture selection (Simple RAG, Hybrid RAG, Re-Ranker Enhanced RAG), side-by-side output comparison, context visualization, and performance metrics analysis. Built with Next.js and Tailwind CSS for the frontend, FastAPI for the backend, and integrating with various LLM providers like Groq, Gemini API, and OpenRouter. Note: While the backend and frontend are hosted successfully, there are currently CORS issues in production that are being resolved.